Vals Multimodal Index leaderboard
As of 6 Nov 2026, the top score on Vals Multimodal Index is 74.2% by Claude Fable 5 (Anthropic), ahead of Claude Opus 5 at 73.9%, across 32 model configurations with a published result (Vals AI, result dated 11 Aug 2026). A composite of Vals AI's image-based benchmarks, weighted by the economic value of the underlying task types. Vals Multimodal Index is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- Claude Fable 5 holds the top Vals Multimodal Index score at 74.2% (Vals AI, 11 Aug 2026).
- Claude Opus 5 is second on Vals Multimodal Index at 73.9% (Vals AI, 11 Aug 2026).
- Vals Multimodal Index: Vals AI's GDP-weighted multimodal composite. Run by Vals AI (Vals AI).
- 32 model configurations have a published Vals Multimodal Index result on BenchLeader (BenchLeader, 6 Nov 2026).
- Vals Multimodal Index does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Vals AI's GDP-weighted multimodal composite. Run by Vals AI.
- Published by
- Vals AI
- Category
- Composite
- Index weight
- Reference only
- Models
- 32
- Data as of
- 6 Nov 2026
Vals AI (vals.ai).
What the test looks like
A composite of Vals AI's image-based benchmarks, weighted by the economic value of the underlying task types.
How it is scored
Vals AI's composite index.
What to keep in mind
A composite; read the component boards for detail.
- 1Claude Fable 574.2%
- 2Claude Opus 573.9%
- 3Kimi K373.4%
- 4GPT-5.6 Sol (max)72.6%
- 5Claude Opus 4.870.9%
- 6Muse Spark 1.269.8%
- 7GPT-5.6 Luna (max)69.1%
- 8Claude Sonnet 568.8%
- 9GPT-5.5 (xhigh)68.1%
- 10Claude Opus 4.767.4%
- 11Muse Spark 1.1 (xhigh)66.7%
- 12Qwen3.8 Max (max)65.4%
- 13Gemini 3.6 Flash (high)65.1%
- 14GPT-5.6 Terra (xhigh)65.1%
- 15Grok 4.5 (high)63.4%
32 of 32
| # | |||||
|---|---|---|---|---|---|
| 1 |  Claude Fable 5 | 74.2% | 66.5 | $7.97 | 2026-08-11 |
| 2 | Claude Opus 5 | 73.9% | 65.2 | $6.14 | 2026-08-11 |
| 3 |  Kimi K3open ↗ | 73.4% | 59.1 | $1.70 | 2026-08-11 |
| 4 |  GPT-5.6 Solmax | 72.6% | 65.4 | $5.36 | 2026-08-11 |
| 5 | Claude Opus 4.8 | 70.9% | 60.0 | $5.46 | 2026-08-11 |
| 6 |  Muse Spark 1.2 | 69.8% | – | $0.506 | 2026-08-11 |
| 7 | GPT-5.6 Lunamax | 69.1% | 56.3 | $0.161 | 2026-08-11 |
| 8 | Claude Sonnet 5 | 68.8% | 55.9 | $6.53 | 2026-08-11 |
| 9 | GPT-5.5xhigh | 68.1% | 64.3 | $3.32 | 2026-08-11 |
| 10 | Claude Opus 4.7 | 67.4% | 63.1 | $4.44 | 2026-08-11 |
| 11 | Muse Spark 1.1xhigh | 66.7% | 59.5 | $0.363 | 2026-08-11 |
| 12 |  Qwen3.8 Maxmax | 65.4% | 58.8 | $1.93 | 2026-08-11 |
| 13 |  Gemini 3.6 Flashhigh | 65.1% | 61.2 | $1.02 | 2026-08-11 |
| 14 | GPT-5.6 Terraxhigh | 65.1% | 60.3 | $0.801 | 2026-08-11 |
| 15 |  Grok 4.5high | 63.4% | 56.9 | $0.911 | 2026-08-11 |
| 16 | Gemini 3.5 Flashhigh | 62.9% | 62.5 | $1.01 | 2026-08-11 |
| 17 | Claude Sonnet 4.6 | 60.6% | 58.2 | $1.58 | 2026-08-11 |
| 18 |  MiniMax M3open ↗ | 60.0% | 56.4 | $1.08 | 2026-08-11 |
| 19 | Kimi K2.6open ↗ | 56.4% | 55.2 | $0.518 | 2026-08-11 |
| 20 | Gemini 3.1 Prohigh | 56.1% | 60.1 | $0.978 | 2026-08-11 |
| 21 | GPT-5.4 Minixhigh | 54.2% | 56.0 | $0.488 | 2026-08-11 |
| 22 | Qwen3.7 Plus | 53.9% | 57.7 | $0.255 | 2026-08-11 |
| 23 | Gemini 3 Flashhigh | 52.2% | 58.3 | $0.287 | 2026-08-11 |
| 24 | Qwen3.6 Plus | 51.5% | 59.1 | $1.12 | 2026-08-11 |
| 25 | Inkling Smallopen ↗ | 50.0% | 52.1 | $0.139 | 2026-08-11 |
| 26 | Inklingopen ↗ | 49.4% | 47.5 | $0.632 | 2026-08-11 |
| 27 | GPT-5.4 Nanohigh | 47.6% | 48.3 | $0.233 | 2026-08-11 |
| 28 | Grok 4.3high | 43.3% | 56.6 | $0.497 | 2026-08-11 |
| 29 | Claude Haiku 4.5thinking | 42.9% | 45.4 | $0.409 | 2026-08-11 |
| 30 | Gemini 3.1 Flash Litehigh | 41.4% | 48.5 | $0.123 | 2026-08-11 |
| 31 | Grok 4.20thinking | 39.1% | 58.4 | $0.398 | 2026-08-11 |
| 32 |  Mistral Medium 3.5highopen | 34.8% | – | $3.45 | 2026-08-11 |
More composite benchmarks · All LLM benchmarks
Related benchmarks
Top head-to-heads on Vals Multimodal Index
Cite as: BenchLeader, “Vals Multimodal Index leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_multimodal_index.
Vals Multimodal Index: questions
- What does Vals Multimodal Index measure?
- A composite of Vals AI's image-based benchmarks, weighted by the economic value of the underlying task types. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on Vals Multimodal Index?
- As of 6 Nov 2026, the highest score on Vals Multimodal Index is 74.2% by Claude Fable 5 (result dated 11 Aug 2026), ahead of Claude Opus 5 at 73.9%. Scores come from Vals AI and are re-read daily.
- Which AI model leads Vals Multimodal Index?
- Claude Fable 5 leads Vals Multimodal Index with 74.2% as of 6 Nov 2026 (result dated 11 Aug 2026), ahead of Claude Opus 5 at 73.9%.
- How many models have Vals Multimodal Index results?
- 32 model configurations have a Vals Multimodal Index result on BenchLeader, all taken from Vals AI.
- Who runs Vals Multimodal Index and how often is it updated?
- Vals Multimodal Index is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does Vals Multimodal Index count toward the BenchLeader Index?
- No. Vals Multimodal Index is shown for reference but left out of the composite index.